Tag
RoleHear is a semi-supervised pipeline that enables a single cache-aware streaming transducer to emit speaker roles inline via lightweight in-vocabulary role tokens, using an offline teacher for pseudo-labeling and an LLM for silver role labels on unlabeled audio.
该论文提出 EGiME(熵引导模型评估),一种基于特征空间聚类结构的半监督准则,无需分类器训练即可在少样本场景下评估预训练模型,在五个基准上与真实准确率相关性达 0.966,并比有监督基线提供更稳定的模型排名。
CoGameReg 提出一种基于合作博弈的协同半监督回归框架,利用 Tri-Game Shapley 机制为异构回归器加权并构建共享伪标签,用于稀疏井标签条件下的地震储层属性预测,并在基准数据集与油田盲井验证中取得更优表现。
This paper proposes a practical recipe for semi-supervised federated ASR using online pseudo-labels with server update stabilization, demonstrating significant improvements over prior methods in both in-domain and cross-domain settings.
This paper introduces R-U-Net, an ECG delineation model that pairs a ResNet-18 encoder with a U-Net decoder, achieving superior performance in semi-supervised learning settings compared to existing methods.
This paper proposes Algebraic Multigrid Acceleration for Efficient Label Spreading (AMELS), a framework that improves scalability and runtime efficiency for label spreading on large-scale datasets by incorporating algebraic multigrid solvers and fast neighborhood graph construction.
This paper introduces Gaussian Bridge Consistency (GBC), a novel framework for long-tailed semi-supervised learning that uses Gaussian feature bridges to improve generalization and reduce confirmation bias, validated on benchmarks like CIFAR10-LT and ImageNet-LT.
The paper introduces C-Score, a diagnostic framework for evaluating pseudo-label-based semi-supervised learning under open-world unlabeled contamination, demonstrating that clean accuracy is insufficient to detect hidden performance degradation.
StreamHear is a semi-supervised pipeline that adapts streaming speech recognition to domain-shifted audio by fine-tuning a teacher model on labeled data, generating pseudo-labels for unlabeled data, and fine-tuning a student model, with a realignment step for better word placement.
This paper introduces CW-BASS v2, a saturation-aware pseudo-label selection method for semi-supervised semantic segmentation that adaptively switches between strict filtering and an adaptive confidence floor depending on the teacher's reliability. It shows improved results over baselines across several benchmarks with DINOv2 teachers.
CLOE is a new semi-supervised anomaly detection method combining an autoencoder with a Christoffel Function-based detector, using a novel loss function to improve representation learning. It achieves state-of-the-art results on high-dimensional tabular data while maintaining simplicity.
Proposes STAD, a semi-supervised framework for distilling text-attributed graphs using Wasserstein distance, dual-pathway encoders, and LLM-based text synthesis to achieve a state-of-the-art performance-compression trade-off.
This paper introduces a decision-aware weak-to-strong (W2S) learning framework that uses limited labeled data to train a weak model, which then generates soft supervision on unlabeled data to train a strong model for improved contextual stochastic optimization. Theoretical bounds and empirical experiments show that abundant unlabeled data can reduce downstream decision risk when the correlation between weak and strong feature representations is small.
This paper proposes a generalized distribution-free semi-supervised learning framework that constructs unbiased risk estimators via linear combinations of component risks, extending PNU learning to multiclass classification while achieving lower variance and providing generalization bounds.
PixCon proposes a clean-positive pixel-contrastive framework for semi-supervised semantic segmentation that guarantees contamination-free positive sets via per-class memory banks, improving accuracy over existing methods on benchmarks like Pascal VOC, Cityscapes, and ADE20K.
PRISM is a novel framework for cross-subject EEG emotion recognition that combines prioritized channel importance weighting via a lightweight expert ensemble with semi-supervised domain adaptation using confidence-filtered pseudo-labels, achieving state-of-the-art results on DEAP, DREAMER, and SEED datasets.
This paper introduces SemiScope, an analysis tool designed to disentangle the effects of classifier tuning from joint SSL and classifier optimization in semi-supervised security classification. Results show that most performance gains attributed to joint optimization can be recovered by simply tuning the classifier and its decision threshold with Bayesian optimization.
This paper proposes a test-time adaptation approach using semi-supervised learning for AI text detection that adapts to continual distribution shifts from new LLMs, adversarial humanization, and temporal drift, outperforming state-of-the-art supervised detectors.
ModTGCN is a modularity-aware graph neural network that jointly optimizes cross-entropy and a modularity-based auxiliary objective to improve text classification by leveraging global community structure in document graphs, achieving consistent gains on five benchmarks.
DeepRHP is a hybrid variational autoencoder that guides the design of random heteropolymers as protein mimics, demonstrated by stabilizing membrane proteins like Aquaporin Z in non-native environments.